© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25994
    Prev
    Next
    INDEX
    Explanations

    university state signal math potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħĭ森
    -0.08
    onnier
    -0.08
    åīįèĢħ
    -0.08
    æĬĺä¸į
    -0.08
    uard
    -0.08
    æŃ£å®Ĺ
    -0.08
    anches
    -0.07
    uez
    -0.07
    inton
    -0.07
    ç¦ıéŁ³
    -0.07
    POSITIVE LOGITS
    éļı
    0.07
    utus
    0.07
     век
    0.06
    表达å¼ı
    0.06
    æ¯ķ
    0.06
    chrif
    0.06
     expression
    0.06
     impart
    0.06
    读æĩĤ
    0.06
    ç¿Ĵ
    0.06
    Activations Density 0.003%

    No Known Activations